© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10992
    Prev
    Next
    INDEX
    Explanations

    terms related to locations or entities with "monte" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or entities, particularly related to brands or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.75
    stood
    -0.72
     patents
    -0.65
    gerald
    -0.64
     allowances
    -0.64
     glim
    -0.62
     compartment
    -0.60
     linemen
    -0.59
    Dir
    -0.59
    ById
    -0.58
    POSITIVE LOGITS
    liction
    0.87
    achine
    0.79
    ois
    0.77
    isd
    0.76
    imester
    0.76
    uces
    0.72
    eus
    0.71
    roe
    0.71
    afort
    0.70
    theless
    0.70
    Activations Density 0.083%

    No Known Activations